Raw vector
CVSS:3.1/AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:HSummary
CVE-2026-20205 is a high-severity Insertion of Sensitive Information into Log File (CWE-532) vulnerability in Splunk MCP Server (inferred from references). Its CVSS base score is 7.2 (High).
Operationally, exploitation aligns with the MITRE ATT&CK technique Unsecured Credentials (T1552); ranked at the 20th percentile by exploit likelihood (below the median); it is not currently listed in the CISA KEV catalog.
This vulnerability is AI-related — categorised as AI Agent Protocols and Integrations; in the Privacy and Disclosure risk domain.
Deeper analysis AI-assisted summary
Synthesised by an AI model from the NVD description and linked references — a reading aid, not an authoritative source.
CVE-2026-20205 is a vulnerability in the Splunk MCP Server app versions below 1.0.3 that allows users with specific privileges to view session and authorization tokens for other users in clear text. The issue stems from sensitive information being logged insecurely, classified under CWE-532, and affects the Splunk platform's internal logging mechanisms. It carries a CVSS v3.1 base score of 7.2 (AV:N/AC:L/PR:H/UI:N/S:U/C:H/I:H/A:H), indicating high impact potential despite requiring elevated privileges.
Exploitation requires a user holding a role with access to the Splunk _internal index or the high-privilege capability mcp_tool_admin. Attackers need either local access to the log files or administrative access to internal indexes, which by default is limited to the admin role. Successful exploitation enables viewing clear-text tokens, potentially allowing token hijacking for unauthorized access, data manipulation, or denial of service, aligning with the high confidentiality, integrity, and availability impacts in the CVSS score.
The Splunk advisory at https://advisory.splunk.com/advisories/SVD-2026-0407 recommends upgrading to version 1.0.3 or later and reviewing roles and capabilities to restrict access to the _internal index to administrator-level roles only. Additional guidance is available in Splunk documentation on defining roles with capabilities and MCP Server admin settings.
OWASP Top 10 for Web (2025)
EU & UK References
- 🇪🇺 ENISA EUVD: EUVD-2026-22935
Vulnerability Data
In Splunk MCP Server app versions below 1.0.3 , a user who holds a role with access to the Splunk `_internal` index or possesses the high-privilege capability `mcp_tool_admin` could view users session and authorization tokens in clear text.<br><br>The vulnerability would…
more
require either local access to the log files or administrative access to internal indexes, which by default only the admin role receives. <br><br>Review roles and capabilities on your instance and restrict internal index access to administrator-level roles. See [Define roles on the Splunk platform with capabilities](https://docs.splunk.com/Documentation/Splunk/latest/Security/Rolesandcapabilities) and [Connecting to MCP Server and Admin settings](https://help.splunk.com/en/splunk-enterprise/mcp-server-for-splunk-platform/connecting-to-mcp-server-and-admin-settings) in the Splunk documentation for more information.
- CWE(s)
AI Security AnalysisAI
- AI Category
- AI Agent Protocols and Integrations
- Risk Domain
- Privacy and Disclosure
- OWASP Top 10 for LLMs 2025
- None mapped
- Classification Reason
- Matched keywords: mcp
Related Threats
MITRE ATT&CK Enterprise Techniques
CVEs Like This One
Affected Assets
Mitigating Controls
Likely Mitigating Controls AI
Per-CVE control mapping for this CVE has not run yet; the list below is derived from the weakness types (CWEs) cited in the NVD entry.
Procedures mandate excluding sensitive data from logs to prevent unauthorized exposure via audit records.
Identifies insertion of sensitive data into logs, allowing detection of unauthorized disclosure.
Cross-organizational coordination enables agreement on what data to include in audit logs, directly reducing insertion of sensitive information.
Identifying logging as a data action allows prevention of sensitive information being inserted into log files.
The process of identifying and eradicating spilled information applies directly to sensitive data inserted into log files.
Specific processing rules for sensitive PII categories commonly include restrictions on logging, making insertion of such data into log files less likely.
PIAs detect planned or existing logging of PII and require removal or protection, preventing insertion of sensitive information into logs.
Limits insertion of sensitive operational details into logs by treating such data as key information requiring protection.
Mitigating Controls (NIST CSF 2.0) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→CSF cross-walk (authority under review) — links open the control.
Secure SDLC practices directly prohibit writing sensitive data to logs; eliminating the weakness satisfies only one narrow slice of the control.
Log generation configuration can and should exclude sensitive data, but the control statement focuses on availability rather than content filtering.
Mitigating Controls (ISO/IEC 27001:2022 Annex A) AI
Derived directly from the weakness types (CWEs) cited in the NVD entry via our AI-authored CWE→ISO cross-walk (authority under review) — links open the control.
Requiring de-identification and privacy controls before logs leave the organization reduces the chance that sensitive data inadvertently captured in logs becomes exposed to external parties.
By defining what records must be kept, where, and for how long, the control discourages the inadvertent inclusion of sensitive information in logs or other externally accessible files that fall outside the formal record system.
Mandating deletion of temporary files and logs that may contain sensitive information prevents those artifacts from remaining accessible after the data is no longer needed.
When log entries are produced from masked data sets, the control prevents the inadvertent insertion of sensitive values into externally accessible log files.
DLP inspection of logs and file transfers can detect and block the inadvertent placement of sensitive tokens or credentials into externally accessible log files before they are written or transmitted.
Requiring restrictions on free-text fields and proper error-message handling stops developers from embedding or leaking sensitive data into logs or diagnostic output.